The traditional annotation-based medical image retrieval faces a problem with competence and precision with the extensive medical image databases. Broad research has been undertaken on Medical image retrieval (MIR) using local, global features of each image, and machine learning algorithms with reliable descriptors have shown the significant improvement of these systems. The proposed method is implemented with a novel approach to address the semantic gap and form efficient texture and shape features clusters. The texture and shape feature vectors are constructed using a novel Relative directional edge binary patterns (RDEBP) and complex Zernike moments. RDEBPs are used to extract the texture features of an image. For every defined square matrix of size 5 × 5, 4 RDEBP patterns are extracted, rich in providing the texture information of an object in the image. The binary patterns are calculated by considering the center pixel’s neighbourhood and relations between neighbour pixels. The complex Zernike moments (ZM) give the shape properties of the object involved in the image. Combining these two features is effectively clustered using the Density-based spatial clustering of applications with noise (DBSCAN) algorithm. Finally, images are retrieved from the closest cluster using the d1-similarity metric concerning the query image. Therefore, the searching time for a query image from the specified cluster is reduced compared to the traditional Content-based image retrieval (CBIR), reflecting excellent response time and retrieval accuracy. Experiments on two databases were performed and confirmed the effectiveness of the proposed work over other state-of-the-art methods. The outcomes of the suggested method are more than 2 to 5% better when compared to the average values produced by other methods.