I think Mahout, a data mining Hadoop-base framework, recommender system algorithms. Check the item-item similarity, which is very close to what you need. 

https://mahout.apache.org/users/recommender/intro-itembased-hadoop.html

Take a look of the paper:  Jeffrey Dean and al.' "MapReduce: Simplified Data Processing on Large Clusters", USENIX Association, OSDI'04: 6th Symposium on Operating Systems Design and Implementation.

I would also suggest Chapters 5-8 in Tom White's Hadoop: The definitive guide, third edition.  This book provides examples.

I am really thankful to Uvernes A Somarriba for his reply. I find this paper is useful for my research.