Image alignment has been studied in different areas of computer vision for hundreds of years, aligning images depicting different scenes remains a challenging problem. Variant to optical ?ow where an image is aligned to its temporally adjacent frame we propose SIFT ?ow [1], a method to align an image to its nearest neighbors in a large database containing huge number of scenes. The SIFT ?ow algorithm consists of matching densely sampled pixel-wise SIFT features between two images. The SIFT features allow unambiguous matching across different scene appearances. The proposed approach combines the concept of Flickr Distance along with the SIFT flow method by determining Flickr Distance between the image concepts. The Flickr distance between two concepts is defined as the Jensen-Shannon (J-S) divergence between their LTVLM. Based on SIFT ?ow, we propose an alignment based large database framework for image analysis and predicting the motion of images. Here the images are taken from the database and provided as nearest neighbors to a query image. This skeleton can be used in the applications such as motion field prediction from a single image, motion prediction satellite image registration and face recognition.