Clustering of Web document has become a vital task, due to the tremendous amount of information that is available on web today. The task of finding suitable information with less time has become a big challenge in information retrieval. So, it's very much necessary to adopt a method that can be used organize the information well. This is possible only when good document groups are formed, which in turn can be achieved when effective and optimized cluster heads are identified. Our concern is to apply an algorithm for web document clustering. The algorithm proposed in this paper is, Cuckoo Search based on Levy Flight. Efficient cluster heads can be located using proposed Cuckoo Search algorithm. And Levy Flight helps us to speed up the local search which also ensures that it covers output domain efficiently. This algorithm is simple, efficient and it is easy to implement. A relative study of the proposed Cuckoo Search based on Levy Flight and K-means algorithm is carried out. The obtained result shows that good performance can be achieved when Cuckoo Search based on Levy Flight algorithm is used for clustering of web documents.