► We contribute a feature selection process based on the correlation of Fractional Anisotropy (FA) and Mean Diffusivity (MD) voxels with the subject class indicative variable. ► We define and test an image co-registration pipeline for anatomical reference of FA and MD volumes which is critical for the feature selection process. ► Voxel sites found by feature selection on a database of Alzheimer's Disease (AD) and healthy controls (HC) agree with previous findings on. ► Classification experiments discriminating AD patients from HC on the basis of FA and MD features compare or improve over results found in the literature for other image modalities (i.e. PET, SPECT). ► We conclude that the proposed features can be used to build classification-based computer aided diagnosis tools. The aim of this paper is to obtain discriminant features from two scalar measures of Diffusion Tensor Imaging (DTI) data, Fractional Anisotropy (FA) and Mean Diffusivity (MD), and to train and test classifiers able to discriminate Alzheimer's Disease (AD) patients from controls on the basis of features extracted from the FA or MD volumes. In this study, support vector machine (SVM) classifier was trained and tested on FA and MD data. Feature selection is done computing the Pearson's correlation between FA or MD values at voxel site across subjects and the indicative variable specifying the subject class. Voxel sites with high absolute correlation are selected for feature extraction. Results are obtained over an on-going study in Hospital de Santiago Apostol collecting anatomical T1-weighted MRI volumes and DTI data from healthy control subjects and AD patients. FA features and a linear SVM classifier achieve perfect accuracy, sensitivity and specificity in several cross-validation studies, supporting the usefulness of DTI-derived features as an image-marker for AD and to the feasibility of building Computer Aided Diagnosis systems for AD based on them.