In this report we study the ways to exploit the vast amount of information inherent in the plenoptic space and constraints of the plenoptic function to improve the efficiency of image retrieval, recognition and matching techniques. The plenoptic space is formed by extending the notion of traditional two-dimensional by adding more dimensions for viewing direction, time and wavelength. Using current hand-held devices' built-in cameras, one can easily capture a large sequence of pictures from a single static scene by moving the camera in one direction, which form a three dimensional plenoptic function.