This paper automates the medical diagnosis process by image registration feed forwarded to object detection with prediction of tumour and cyst by using K-means clustering over HSV colour features. Diagnosis of life killer disease is a complex process which requires bio-medical image such as MRI, CT, and endoscopy etc. Many biomedical images are used for the same case to predict the disease. Because of different view point of different photographic sensors at different time obtained medical images are not aligned. So the manual diagnosis makes harder because of the images are not registered or not aligned properly. The inherent cause is the distortion of the imaging signal where object may be miss-transformed due to different camera focus and projection. Image registration is an essence to bypass the non-alignment issue. Here, we have proposed and analysed a combined solution towards the miss aligned object or region of interest by performing reverse geometric transformation with different angle to produce the better perspective image for diagnosis which is feed forwarded to HSV colour model-based segmentation to predict the cyst and tumour presence.