CBIR technique is becoming increasingly important in medical field in order to store, manage, and retrieve image data based on user query. In order to reduce the computational time for SVM training we introduce unsupervised clustering before supervised classification. Searching is done by means of matching the image features such as texture, shape, or different combinations of them. Texture features play an important role in computer vision, image processing and pattern recognition. We introduce a novel method of using SVM(Support Vector machine) classifier followed by KNN(K-nearest neighbour) for CBIR using texture and shape feature.