Clusters don't work like that. Clusters work by taking a large workload, breaking it into small pieces and farming them out to run on each of the clustered nodes. A cluster doesn't add processing power, it doesn't add RAM and it doesn't add speed for a general purpose workload.
The clustered workload has to be optimised for clustering and that's the hard part of the puzzle. Can you divide your database into partitions so that each cluster works on just a subset of data, can you aggregate the results set?
Note: Any requirement to use a crystal ball or mind reading will result in me ignoring your question.
I'll do your homework for you for a suitable fee.
Any DMs sent on Twitter will be answered next month.
All non-medical doctors are on my foes list.