SA,
how are u girls? hope you are fine :)

our objective

• Is to retrieve most similar cases(images) to the one queried by doctor to know its diagnosis
• Having a collection of feature vectors stored in a database in a d-dimensional space, image retrieval is done using k-nearest neighbors algorithm.
• The most straight forward way is to sequentially compare all points using the given distance measure.
• This linear search takes O(n) time, which will be so slow for large databases

K-d tree

• kd-tree or k-dimensional tree is a space partitioning data structure for organizing points in a k-dimensional space.
• kd-trees are efficient methods of finding nearest neighbors in high dimensional spaces

Resources
To read more..
The wikipedia link: http://en.wikipedia.org/wiki/Kd-tree
you can find kd tree implementation here: http://www.cs.wlu.edu/~levy/software/kd/